语言模型是超级马里奥：从同源模型中吸收能力如同免费午餐
Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch
AI总结：
本文提出DARE方法，通过随机丢弃并重缩放delta参数来稀疏化同源微调模型参数，无需重新训练即可将多个任务模型融合为单一多能力语言模型，并在大规模模型上取得超越源模型的性能。
摘要：
在本文中，我们揭示语言模型（LMs）可以通过吸收同源模型的参数来获得新能力，而无需重新训练或使用GPU。我们首先引入DARE，在不影响监督微调（SFT）语言模型能力的情况下，将大部分delta参数（即微调参数与预训练参数之间的差异）置为零，该方法以比例$p$随机丢弃delta参数，并将剩余参数按$1 / (1 - p)$重新缩放以近似原始嵌入。然后，我们将DARE作为一个通用的即插即用模块，对多个SFT同源模型的delta参数进行稀疏化，以缓解参数干扰，并通过参数融合将它们合并为单一模型。我们在基于编码器和解码器的语言模型上进行了实验，结果表明：（1）SFT delta参数的取值范围通常很小（在0.002以内），且存在极大的冗余，DARE可以轻松消除其中90%甚至99%的参数；（2）DARE可以将多个任务特定的语言模型合并为一个具有多种能力的语言模型。值得注意的是，这一现象在大规模语言模型中更为显著，合并后的语言模型展现出超越任何源模型性能的潜力，这提供了一项新发现。我们还利用DARE创建了一个合并语言模型，该模型在Open LLM Leaderboard上位列70亿参数模型的第一名。
英文摘要：
In this paper, we unveil that Language Models (LMs) can acquire new capabilities by assimilating parameters from homologous models without retraining or GPUs. We first introduce DARE to set most delta parameters (i.e., the disparity between fine-tuned and pre-trained parameters) to zeros without affecting the abilities of Supervised Fine-Tuning (SFT) LMs, which randomly Drops delta parameters with a ratio $p$ And REscales the remaining ones by $1 / (1 - p)$ to approximate the original embeddings. Then, we use DARE as a versatile plug-in to sparsify delta parameters of multiple SFT homologous models for mitigating parameter interference and merge them into a single model by parameter fusing. We experiment with encoder- and decoder-based LMs, showing that: (1) SFT delta parameter value ranges are typically small (within 0.002) with extreme redundancy, and DARE can effortlessly eliminate 90% or even 99% of them; (2) DARE can merge multiple task-specific LMs into one LM with diverse capabilities. Notably, this phenomenon is more pronounced in large-scale LMs, where the merged LM reveals the potential to surpass the performance of any source LM, providing a new discovery. We also utilize DARE to create a merged LM that ranks first among models with 7 billion parameters on the Open LLM Leaderboard.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
